© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 20306
    Prev
    Next
    INDEX
    Explanations

    instances where the text advises skipping or jumping over certain content

    oai_token-act-pair · gpt-3.5-turbo

    instructions or suggestions to skip sections of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amen
    -0.77
    lee
    -0.73
    orc
    -0.72
    lie
    -0.69
    lisher
    -0.68
    oran
    -0.68
    crim
    -0.67
    Reviewer
    -0.67
    rador
    -0.67
    eer
    -0.65
    POSITIVE LOGITS
     altogether
    0.87
     ahead
    0.77
     breakfast
    0.75
     overboard
    0.73
     vacations
    0.69
     puberty
    0.69
    ichi
    0.68
     detection
    0.67
     bothering
    0.67
     meals
    0.67
    Activations Density 0.039%

    No Known Activations